© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 1915
    Prev
    Next
    INDEX
    Explanations

    phrases related to the name "Grace"

    oai_token-act-pair · gpt-3.5-turbo

    the occurrences of the name "Grace."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ickr
    -0.73
    rd
    -0.66
    abol
    -0.62
     razor
    -0.60
    actic
    -0.60
    onut
    -0.60
     proprietary
    -0.58
     extrap
    -0.58
    crim
    -0.58
     OECD
    -0.57
    POSITIVE LOGITS
     Grace
    1.16
    fully
    0.96
    ful
    0.96
    fulness
    0.84
    veland
    0.79
    ibility
    0.78
    hurst
    0.76
    ilee
    0.74
    eous
    0.73
    ira
    0.72
    Activations Density 0.009%

    No Known Activations